Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.
Optional enforcing hooks for platform-skills: self-improve lifecycle capture and the ai-governance policy gate (active only in projects with a .ai-governance.yaml). Separate from platform-skills because plugin hooks run in every session for everyone who enables them.
One tool-agnostic ruleset for AI coding agents, loaded at session start instead of by hand: boundaries, security, a verification gate, the lazy-senior-dev coding ladder, commit conventions, plus on-demand modules across the stack.
Make a codebase agent-ready with progressive-disclosure documentation, domain context, regression-aware quality gates, and stack-specific skill recommendations. Uses AGENTS.md directly with Claude Code 2.1.277+ without requiring a CLAUDE.md symlink.
AI agent skill for Catalyst by Zoho — the agent-ready, full-stack cloud. Covers all services, SDKs, CLI, architecture patterns, pricing, migration guides, and Zoho MCP tool-based resource management.
Skills for deploying and maintaining AUP Learning Cloud: install, deploy, configure courses, build images, upgrade, troubleshoot, configure auth, manage users and quota, monitor, expose with TLS/storage, configure repo cloning, and author courses for the multi-node JupyterHub-on-k3s platform for AMD GPUs.
Longbridge securities skill family (v2): 13 consolidated skills replacing the previous 127-skill set. Full coverage of market data, fundamentals, research, portfolio & account, quantitative strategies, and more. Requires reinstall (not just update) when upgrading from v1.x — see scripts/update.sh.
While your Claude works, a small window opens and puts you on a call with a stranger whose Claude is also working. It closes when either Claude finishes. Nothing about your task is ever shared.
MCP tools for LTspice/ngspice circuit simulation and LTspice .asc schematic editing. Structured results include per-device operating points (gm/gds/vth) by device name, without parsing raw files. Requires uv and a simulator (LTspice or ngspice) on the host; the server is fetched from PyPI via uvx on first use.
Expert FinOps guidance for cloud, AI, SaaS and data-platform spend. Ask Claude how to reduce a bill, size a commitment, allocate shared costs or justify AI spend, and it answers with billing mechanics, decision rules and worked examples, not generic advice.
Cloud: AWS, Azure, GCP, OCI, Kubernetes and on-premises or hybrid estates, including Savings Plans, Reserved Instances, Azure Hybrid Benefit and contract negotiation.
AI: Anthropic, Bedrock, Azure OpenAI, Vertex AI, open-weight model APIs, AI coding tools, agent costs, self-hosted vs managed inference.
Data platforms: Databricks, Snowflake, Microsoft Fabric.
FinOps practice: allocation, showback and chargeback, forecasting, operating model, FOCUS multi-cloud cost data, tagging, anomalies, KPIs, workload onboarding, SaaS and IT asset management, GreenOps.
Waste playbooks: 44 runbooks for waste patterns such as idle NAT gateways, orphaned disks, snapshot sprawl, unused reservations, oversized GPUs and coding-agent token waste. Each gives a detection query to run in your account, the fix, and a confidence level.
Good to know: this plugin adds instructions only and does not connect to your cloud accounts. Open source (CC BY-SA 4.0), maintained by OptimNow and updated weekly.